Training in progress, step 10000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b561852c7a2760391730922ad15cca84211b928b3355d82427553ddf0689dc1a
+oid sha256:cdf4166a6f103434fb1d190f5ce96cea034d24734388bb548b0de25b70e063aa
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:935d9a8a7ad0a5baaf59253fd1faac16f656f3e19ec1cf0e6cdf507d54ae8d9a
+oid sha256:48d0fa2636a55e80f60c35237b2f8e5314ea27a4424dbc5120af876ed27ace55
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1128d67de3d4d8e3dd8bc8b4bca4f59bef7d1d2c35b978700b48aaaa3a3cb733
+oid sha256:6b7e320b5a2475507aebb5f1ef7a9c98d12600ef0165cc1de949f181761d986b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1d4e0d33a262ad4f64c2ce77b757798ccbd7d82035d16a8a99e7def08d07a9c
+oid sha256:28e35c5a0c1eb4f922a2e3785d5afca45020e4d0fc6713cc20aea6ed31f143e1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.03963331878185272,
-  "best_model_checkpoint": "doc-topic-model_eval-01_train-00/checkpoint-9000",
-  "epoch": 4.437869822485207,
+  "best_metric": 0.038666386157274246,
+  "best_model_checkpoint": "doc-topic-model_eval-01_train-00/checkpoint-10000",
+  "epoch": 4.930966469428008,
   "eval_steps": 1000,
-  "global_step": 9000,
+  "global_step": 10000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -241,6 +241,32 @@
       "eval_samples_per_second": 553.061,
       "eval_steps_per_second": 2.182,
       "step": 9000
+    },
+    {
+      "epoch": 4.684418145956608,
+      "grad_norm": 0.3310143053531647,
+      "learning_rate": 1.906311637080868e-05,
+      "loss": 0.0343,
+      "step": 9500
+    },
+    {
+      "epoch": 4.930966469428008,
+      "grad_norm": 0.5156289935112,
+      "learning_rate": 1.90138067061144e-05,
+      "loss": 0.0343,
+      "step": 10000
+    },
+    {
+      "epoch": 4.930966469428008,
+      "eval_accuracy": 0.9870459344926796,
+      "eval_f1": 0.5692336695258743,
+      "eval_loss": 0.038666386157274246,
+      "eval_precision": 0.7471235927254732,
+      "eval_recall": 0.4597639893414541,
+      "eval_runtime": 14.4377,
+      "eval_samples_per_second": 561.722,
+      "eval_steps_per_second": 2.216,
+      "step": 10000
     }
   ],
   "logging_steps": 500,
@@ -269,7 +295,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 203651375179716.0,
+  "total_flos": 226383014056572.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null